Visualized Onomatopoeia Thesaurus Maps Based on Deep Autoencoder

Onomatopoeias can simply describe sounds or state of things. Therefore they are often used in Japanese daily conversation. On the other hand, one of the problems, which Japanese learners face, is the lack of ways to learn Japanese onomatopoeias. This study proposes a thesaurus map which can describe semantic relationship among onomatopoeias. Our proposed method can transform the onomatopoeia into a 2D-vector and assign it on the map. In our experiment, we examined whether the map can describe the semantic relationship as local distance on the map. The experiment utilized onomatopoeia samples which represent "human motion" to evaluate the map.